Juhamatti Saari

Juhamatti Saari

Auto-generated profile, based on publicly available information

Juhamatti Saari

Division of Operation, Maintenance and Acoustics Luleå University of Technology Luleå SE 97187 Sweden

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019 in Measurement
Verified
Journal Article
Closed access
JSJuhamatti Saari
Juhamatti Saari
DSDaniel Strömbergsson
Daniel Strömbergsson
JLJan Lundberg
Jan Lundberg
ATAllan Thomson
Allan Thomson

7 August 2019 in Wind Energy
Verified
Journal Article
Closed access
DSDaniel Strömbergsson
Daniel Strömbergsson
PMPär Marklund
Pär Marklund
KBKim Berglund
Kim Berglund
JSJuhamatti Saari
Juhamatti Saari
ATAllan Thomson
Allan Thomson


1 January 2016 in International Journal of Industrial and Systems Engineering
Verified
Journal Article
Closed access
ALArto Laukka
Arto Laukka
JSJuhamatti Saari
Juhamatti Saari
JRJari Ruuska
Jari Ruuska
EJEsko Juuso
Esko Juuso
SLSulo Lahdelma
Sulo Lahdelma
Condition-based maintenance (CBM) can significantly reduce maintenance costs by identifying upcoming needs but requires data fusion and more real-time measurements. Typical measurement variables are vibration, temperature, different speeds and pressures. The project aims to develop a solution framework for combining condition monitoring (CM) and process data to integrate CBM with control and timing of the maintenance actions. The use of on-line and periodic CM measurements requires advanced signal processing and feature extraction. This paper focuses on implementing the measurement system in a case study conducted in Pyhäsalmi mine with Sandvik load haul dump (LHD) machinery. The measurement monitoring system was installed on LHD front axle, which is among the most critical parts in LHD machines. A feasible solution was found in the harsh underground conditions. The working stages can be identified from the signals and the measurements are suitable for the development of the condition and stress indices.

1 August 2018 in Insight - Non-Destructive Testing and Condition Monitoring
Verified
Journal Article
Closed access
JSJ Saari
J Saari
JLJ Lundberg
J Lundberg
JOJ Odelius
J Odelius
MRM Rantatalo
M Rantatalo
Identification of component faults using automated condition monitoring methods has a huge potential to improve the prediction of machine failures. The ongoing development of the Internet of Things (IoT) will support and benefit feature selection and improve preventative maintenance decision making. However, there may be problems with the selection of features that best describe a specific fault and remain valid even when the operation mode is changing (for example different levels of load). In this study, features were extracted from vibration signals using wavelet analysis; a feature subset was selected using the random forest ensemble technique. Three different datasets were created where the load of the system was changing while the rotational speed remained the same. The tests were repeated five times by first recording the nominal condition and then introducing four faults: angular misalignment; offset misalignment; partially broken gear tooth failure; and macro-pitting of the gear. To improve previous feature selection techniques, a method is proposed where, before training a classifier, the most promising features are compared at different degrees of torsional load. The results indicate that the proposed method of using random forests to select top variables can help to choose good features that may not have been considered in manual feature selection or in individual load zones.